Cache exact Frontier EP lane predictions

2026-07-15 22:07:40 +08:00
parent ed500fa016
commit 5fadc86edd
2 changed files with 18 additions and 0 deletions
--- a/runs/frontier-multicase-sufficiency-v0/best_effort/fixed_cohort_rank.py
+++ b/runs/frontier-multicase-sufficiency-v0/best_effort/fixed_cohort_rank.py
@@ -631,6 +631,7 @@ def run_frontier(args: argparse.Namespace) -> Path:
            "quantization": "block_fp8_w8a8_dynamic_with_bf16_output_accumulation",
            "execution_profiles": "community_vllm_0.10.2_serving_entrypoints",
            "moe_ep_prefill": "global_routing_then_slowest_local_ep_lane",
+            "moe_ep_critical_lane_cache": "exact_(total_routed_tokens,layer_id)_memoization",
            "kv_blocks": "measured_community_vllm_and_fixed_per_topology",
            "cpu_overhead_modeling": "disabled_no_native_community_vllm_records",
            "end_to_end_action_specific_calibration": False,